// head_to_head
Kimi K2.7 Code vs Nemotron 3 Ultra
Published LiveBench scores across all seven categories, live list pricing, context windows, and the measured cost of a point of capability — for both models, side by side.
Kimi K2.7 Code scores higher, Nemotron 3 Ultra costs less — it depends on your workload.
Kimi K2.7 Code is ahead by 1.1 points overall, and Nemotron 3 Ultra lists 29% cheaper per blended million tokens. Whether 1.1 points is worth that depends on how much a wrong answer costs you. The two cost measures disagree here, which is worth knowing: Nemotron 3 Ultra has the lower sticker price, but Kimi K2.7 Code earns each point of capability for less — $0.0545 against $0.2118 — because per-token rates do not predict how many tokens a model actually spends on a task.
moonshotai
Kimi K2.7 Code
- Blended / 1M
- $1.35
- Context
- 262K
- Released
- Jun 12, 2026
- Overall score
- 68.4
nvidia
Nemotron 3 Ultra
- Blended / 1M
- $1.05
- Context
- 262K
- Released
- Jun 4, 2026
- Overall score
- 67.4
Specs and pricing
| Metric | Kimi K2.7 Code | Nemotron 3 Ultra |
|---|---|---|
| LiveBench overall Mean of the seven LiveBench category scores, 0–100. Higher is better. | 68.4win | 67.4 |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | $0.0545win | $0.2118 |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $1.35 | $1.05win |
| Input price / 1M | $0.706 | $0.600win |
| Output price / 1M | $3.30 | $2.40win |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | $0.180 | $0.120win |
| Context window | 262K | 262K |
| Max output tokens | 236Kwin | 183K |
Benchmarks by category
An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — Kimi K2.7 Code on top, Nemotron 3 Ultra below, both out of 100.
What each one costs to run
Per-token prices are hard to feel. These are monthly list costs for both models across five workload shapes, using each provider's published cached-input rate where there is one.
| Workload | Kimi K2.7 Code | Nemotron 3 Ultra |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $395.60/mo | $301.44/mo |
| RAG assistant 8K in / 600 out × 100K requests | $552.48/mo | $432.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $534.29/mo | $403.20/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $927.39/mo | $756.00/mo |
| Bulk classification 500 in / 20 out × 5M requests | $1,832/mo | $1,500/mo |
Which should you pick?
You are running this at volume
Kimi K2.7 Code
Lowest measured cost per point of capability at $0.0545 per point — the gap compounds with every request.
Quality matters more than the bill
Kimi K2.7 Code
Highest overall LiveBench score of the two at 68.4.
The workload is coding or agentic work
Kimi K2.7 Code
Leads on agentic coding — 45.7 against 38.7.
You are cost-constrained
Nemotron 3 Ultra
Cheaper on blended list price at $1.05 per million tokens.
Kimi K2.7 Code vs Nemotron 3 Ultra FAQ
Which is better, Kimi K2.7 Code or Nemotron 3 Ultra?
Kimi K2.7 Code scores higher, Nemotron 3 Ultra costs less — it depends on your workload. Kimi K2.7 Code is ahead by 1.1 points overall, and Nemotron 3 Ultra lists 29% cheaper per blended million tokens. Whether 1.1 points is worth that depends on how much a wrong answer costs you. The two cost measures disagree here, which is worth knowing: Nemotron 3 Ultra has the lower sticker price, but Kimi K2.7 Code earns each point of capability for less — $0.0545 against $0.2118 — because per-token rates do not predict how many tokens a model actually spends on a task.
Is Kimi K2.7 Code cheaper than Nemotron 3 Ultra?
Nemotron 3 Ultra is cheaper. On a 3:1 input:output blend, Kimi K2.7 Code lists at $1.35 per million tokens and Nemotron 3 Ultra at $1.05 — Nemotron 3 Ultra is 29% cheaper. Input and output are priced separately — Kimi K2.7 Code charges $0.706 in and $3.30 out, Nemotron 3 Ultra charges $0.600 and $2.40 — so the model that looks cheaper flips depending on how output-heavy your workload is.
Kimi K2.7 Code vs Nemotron 3 Ultra: which scores higher on benchmarks?
Kimi K2.7 Code scores 68.4 and Nemotron 3 Ultra scores 67.4 overall on LiveBench, the mean of its seven categories. That is a 1.1-point lead for Kimi K2.7 Code. Category scores differ from the overall figure — a model can lead on reasoning and trail on coding, which the per-category table above breaks out.
Which gives better value for money, Kimi K2.7 Code or Nemotron 3 Ultra?
Kimi K2.7 Code. Cost per point divides the measured dollars LiveBench spent running the benchmark by the score it earned, so it captures something token pricing misses: a reasoning model can emit many times more tokens than its per-token rate suggests. Kimi K2.7 Code works out at $0.0545 per point and Nemotron 3 Ultra at $0.2118.
Does Kimi K2.7 Code or Nemotron 3 Ultra have a bigger context window?
They are effectively the same — 262K for Kimi K2.7 Code and 262K for Nemotron 3 Ultra.
Do Kimi K2.7 Code and Nemotron 3 Ultra support prompt caching?
Both publish a cached-input rate: $0.180 per million for Kimi K2.7 Code and $0.120 for Nemotron 3 Ultra, against full input rates of $0.706 and $0.600. On a workload with a long stable prefix — a system prompt, a tool schema, a retrieved corpus — that changes the economics more than the headline price does.
Related comparisons
How these numbers are produced
- Price — provider list price from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores — LiveBench release 2026-06-25, using their own category map. Each model shows its strongest published run. A blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
- “Win” — awarded only past a threshold: one full point on a benchmark score, 10% on a price, 25% on a context window. Anything tighter reports as a tie, because effort settings alone move a LiveBench score by more than that.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.